Screening of COVID-19 based on the extracted radiomics features from chest CT images

Abstract

BACKGROUND AND OBJECTIVE: Radiomics has been widely used in quantitative analysis of medical images for disease diagnosis and prognosis assessment. The objective of this study is to test a machine-learning (ML) method based on radiomics features extracted from chest CT images for screening COVID-19 cases. METHODS: The study is carried out on two groups of patients, including 138 patients with confirmed and 140 patients with suspected COVID-19. We focus on distinguishing pneumonia caused by COVID-19 from the suspected cases by segmentation of whole lung volume and extraction of 86 radiomics features. Followed by feature extraction, nine feature-selection procedures are used to identify valuable features. Then, ten ML classifiers are applied to classify and predict COVID-19 cases. Each ML models is trained and tested using a ten-fold cross-validation method. The predictive performance of each ML model is evaluated using the area under the curve (AUC) and accuracy. RESULTS: The range of accuracy and AUC is from 0.32 (recursive feature elimination [RFE]+Multinomial Naive Bayes [MNB] classifier) to 0.984 (RFE+bagging [BAG], RFE+decision tree [DT] classifiers) and 0.27 (mutual information [MI]+MNB classifier) to 0.997 (RFE+k-nearest neighborhood [KNN] classifier), respectively. There is no direct correlation among the number of the selected features, accuracy, and AUC, however, with changes in the number of the selected features, the accuracy and AUC values will change. Feature selection procedure RFE+BAG classifier and RFE+DT classifier achieve the highest prediction accuracy (accuracy: 0.984), followed by MI+Gaussian Naive Bayes (GNB) and logistic regression (LGR)+DT classifiers (accuracy: 0.976). RFE+KNN classifier as a feature selection procedure achieve the highest AUC (AUC: 0.997), followed by RFE+BAG classifier (AUC: 0.991) and RFE+gradient boosting decision tree (GBDT) classifier (AUC: 0.99). CONCLUSION: This study demonstrates that the ML model based on RFE+KNN classifier achieves the highest performance to differentiate patients with a confirmed infection caused by COVID-19 from the suspected cases.

Reliability of Machine Learning in Eliminating Data Redundancy of Radiomics and Reflecting Pathophysiology in COVID-19 Pneumonia: Impact of CT Reconstruction Kernels on Accuracy

“…Recovery vs death 0.85 [21] Radiomics 0.81 [22] Radiomics 0.84-0.87 [23] Radiomics and clinical features 88 88 89 0.95 [24] Radiomics + CT images, age, CRP 14 day outcomes 88.8 73.0 0.88 [25] Radiomics PCR negative status during treatment 60.0 63.0 0.81 [21] Radiomics ICU admission 0.84 [22] Radiomics 0.81 1.00 [30] 85.2 69.5 91.6 0.88 [31] 1.00 [32] COVID-19 vs Influenza A pneumonia 0.87 [33] Radiomics + CT images 90.3 89.9 90.7 0.96 * All the papers reported findings on radiomics retrieved from lung CT except for [28] where radiograms were used values.…”

Computer-aided diagnostic for classifying chest X-ray images using deep ensemble learning

“…By this reason, previous studies analyses the diagnosis of lung diseases, such as COVID, by using CT [ 17 , 18 ]. The availability of large datasets with medical images, the advances in deep learning, and the computer power evolution have boosted the development of computer medical aid systems to assist experts to make their diagnosis [ 19 ].…”

Detecting COVID-19 in chest images based on deep transfer learning and machine learning algorithms

“…Therefore, an accurate and fast method is required to overcome this problem. Moreover, CT images provide quantitative information, but only qualitative information is reported due to the lack of computerized tools to process [14]. Image processing is a technique to extract useful information from an image.…”